From prediction markets to interpretable collective intelligence

TL;DR

This paper proposes a mechanism for creating interpretable, self-resolving prediction markets with play money that incentivize experts to share information and estimate probabilities of logical propositions, aiming to improve collective problem-solving.

Contribution

It introduces a novel prediction market framework that elicits explicit probabilistic information from experts without assuming Bayesian behavior, enhancing collective intelligence.

Findings

The proposed mechanism can incentivize experts to share truthful information.

It enables the elicitation of explicit probabilities and collective information.

Potential applications include scientific and medical problem-solving.

Abstract

We outline how to create a mechanism that provides an optimal way to elicit, from an arbitrary group of experts, the probability of the truth of an arbitrary logical proposition together with collective information that has an explicit form and interprets this probability. Namely, we provide strong arguments for the possibility of the development of a self-resolving prediction market with play money that incentivizes direct information exchange between experts. Such a system could, in particular, motivate simultaneously many experts to collectively solve scientific or medical problems in a very efficient manner. We also note that in our considerations, experts are not assumed to be Bayesian.